Version Update:
Further training with more diverse data and more complete training process. Had better results with it.
I had good success with already positioned initial frames and combined with "CausVid"; 3-5 steps usually enough when using with it.
As usual I just picked some generated images randomly to animate from trending page, kudos to creators.
No trigger word used directly but 'bouncy walking' is pretty common. I recommend focusing on the action describing the subject with the concept related words. No nsfw included in the training set.
Here’s an example prompt I used in some of these generations—feel free to alter it heavily:
A woman with long blonde hair, wearing a black t-shirt, orange tight shorts, white socks, and beige shoes, is bouncy walking down a city street. Her large, round ass are prominent as she walks away from the camera. She is on a cobblestone street with cars and buildings on either side.Please use the model responsibly. No real person faces were used in the training.